Semi-local Affine Parts for Object Recognition

Svetlana Lazebnik 1 Cordelia Schmid 2, * Jean Ponce 1
* Auteur correspondant
2 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : This paper proposes a new approach for finding expressive and geometrically invariant parts for modeling 3D objects. The approach relies on identifying groups of local affine regions (image features having a characteristic appearance and elliptical shape) that remain approximately affinely rigid across a range of views of an object, and across multiple instances of the same object class. These groups, termed semi-local affine parts, are learned using correspondence search between pairs of unsegmented and cluttered input images, followed by validation against additional training images. The proposed approach is applied to the recognition of butterflies in natural imagery.
Type de document :
Communication dans un congrès
Andreas Hoppe and Sarah Barman and Tim Ellis. British Machine Vision Conference (BMVC '04), Sep 2004, Kingston, United Kingdom. The British Machine Vision Association (BMVA), pp.779--788, 2004, 〈http://www.bmva.org/bmvc/2004/BMVC_2004a.html〉
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548542
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 09:09:32
Dernière modification le : mercredi 11 avril 2018 - 01:56:10
Document(s) archivé(s) le : lundi 21 mars 2011 - 03:12:40

Fichier

bmvc04.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00548542, version 1

Collections

IMAG | INRIA | UGA

Citation

Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. Semi-local Affine Parts for Object Recognition. Andreas Hoppe and Sarah Barman and Tim Ellis. British Machine Vision Conference (BMVC '04), Sep 2004, Kingston, United Kingdom. The British Machine Vision Association (BMVA), pp.779--788, 2004, 〈http://www.bmva.org/bmvc/2004/BMVC_2004a.html〉. 〈inria-00548542〉

Partager

Métriques

Consultations de la notice

704

Téléchargements de fichiers

1199